Research Scientist, Gemini Horizon, DeepMind

Responsibilities

• Improve Gemini with new Reinforcement Learning (RL) environments, evaluations, changes to the RL recipe, or ideas.
• Explore domains where Gemini should be superhuman (e.g., security, hardware, performance engineering, scientific computing, or something we have not thought of) and build the evaluations that show the gap is real.
• Invent new ways of manufacturing hard problems and the graders that make them verifiable.
• Evaluate and train Gemini on your environments, read the trajectories to see what it is actually learning, and land what transfers into production.
• Contribute to identifying and delivering breakthroughs for Gemini.
• - Improve Gemini with new Reinforcement Learning (RL) environments, evaluations, changes to the RL recipe, or ideas. - Explore domains where Gemini should be superhuman (e.g., security, hardware, performance engineering, scientific computing, or something we have not thought of) and build the evaluations that show the gap is real. - Invent new ways of manufacturing hard problems and the graders that make them verifiable. - Evaluate and train Gemini on your environments, read the trajectories to see what it is actually learning, and land what transfers into production. - Contribute to identifying and delivering breakthroughs for Gemini.

Minimum qualifications:

Preferred qualifications:

Qualifications

• Minimum qualifications: - PhD degree in Computer Science, Artificial Intelligence, Machine Learning, a related technical field, or equivalent practical experience. - 1 year experience with Generative AI, Large Language Models, natural language processing, or Agent-based systems. - 1 year of experience working on modern large language model post-training (e.g., SFT, RLHF, DPO, PPO), model alignment, or core generative model development in an industry AI lab, research institute, or frontier AI organization. Preferred qualifications: - Experience with reinforcement learning for LLM post-training.